OSC: Cognitive Orchestration through Dynamic Knowledge Alignment in Multi-Agent LLM Collaboration

2025-09-05

AI Summary

To address the limited collaboration depth and inefficient linguistic interaction among large language model (LLM)-based agents in multi-agent systems, this paper proposes the OSC framework, which enables cognitive coordination via dynamic knowledge alignment. Its core innovation is the Collaborator Knowledge Model (CKM), which continuously models peer agents’ cognitive states and guides adaptive communication behavior—via cognitive gap analysis, dynamic content focusing, stylistic adaptation, and hierarchical detail optimization—through a reinforcement learning policy. OSC bridges the collaboration gap between agent selection and result aggregation, substantially improving cooperative efficiency and solution quality on complex reasoning tasks. Empirical evaluation across multiple benchmarks demonstrates significant gains in task accuracy and reductions in both communication rounds and message length. OSC thus achieves, for the first time, a paradigm shift from parallel individual reasoning to deep cognitive collaboration within agent teams.

Technology Category

• Multiagent Systems: Agent Communication
• Cognitive Modeling & Cognitive Systems: Agent Architectures
• Machine Learning: Large Multimodal Models (LMMs)

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems
• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation

Abstract

This paper introduces OSC (Orchestrating Cognitive Synergy), a knowledge-aware adaptive collaboration framework designed to enhance cognitive synergy in multi-agent systems with large language models. While prior work has advanced agent selection and result aggregation, efficient linguistic interactions for deep collaboration among expert agents remain a critical bottleneck. OSC addresses this gap as a pivotal intermediate layer between selection and aggregation, introducing Collaborator Knowledge Models (CKM) to enable each agent to dynamically perceive its collaborators' cognitive states. Through real-time cognitive gap analysis, agents adaptively adjust communication behaviors, including content focus, detail level, and expression style, using learned strategies. Experiments on complex reasoning and problem-solving benchmarks demonstrate that OSC significantly improves task performance and communication efficiency, transforming "parallel-working individuals'' into a "deeply collaborative cognitive team.'' This framework not only optimizes multi-agent collaboration but also offers new insights into LLM agent interaction behaviors.

Problem

• Enhancing cognitive synergy in multi-agent LLM systems through dynamic collaboration
• Addressing inefficient linguistic interactions among expert agents in deep collaboration
• Bridging the gap between agent selection and result aggregation with knowledge alignment

Innovation

• Dynamic knowledge alignment for cognitive synergy
• Real-time cognitive gap analysis for adaptive communication
• Collaborator Knowledge Models for cognitive state perception